Evidential two-step tree species recognition approach from leaves and bark

作者：

Highlights：

• Two step classification approach is introduced for tree species recognition.

• The theory of belief functions is used to reduce species confusions.

• An efficient mass distribution estimation algorithm is proposed for the evidential kNN.

• The approach can be developed as a mobile application that does not need internet.

摘要

•Two step classification approach is introduced for tree species recognition.•The theory of belief functions is used to reduce species confusions.•An efficient mass distribution estimation algorithm is proposed for the evidential kNN.•The approach can be developed as a mobile application that does not need internet.

论文关键词：Tree species recognition,Two-step classification,Theory of belief functions,Mass estimation,k nearest neighbors

论文评审过程：Received 8 April 2019, Revised 2 December 2019, Accepted 19 December 2019, Available online 25 December 2019, Version of Record 30 December 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113154